6 papers
Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems
Zhiqian Zhang, Xu Zhao, Xiaoqing Xu +5
In recent years, multimodal large models have continued to improve on general benchmarks. However, in real-world content moderation and adversarial settings, mainstream models stil…
TWEO: Transformers Without Extreme Outliers Enables FP8 Training And Quantization For Dummies
Guang Liang, Jie Shao, Ningyuan Tang +2
Native FP8 support in modern hardware is essential for training large Transformers, but is severely hindered by extreme activation outliers. Existing solutions either rely on compl…
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
Junbo Niu, Zheng Liu, Zhuangcheng Gu +58
We introduce MinerU2.5, a 1.2B-parameter document parsing vision-language model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational effi…
YOLOv8-SMOT: An Efficient and Robust Framework for Real-Time Small Object Tracking via Slice-Assisted Training and Adaptive Association
Xiang Yu, Xinyao Liu, Guang Liang
Tracking small, agile multi-objects (SMOT), such as birds, from an Unmanned Aerial Vehicle (UAV) perspective is a highly challenging computer vision task. The difficulty stems from…
MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results
Yuki Kondo, Norimichi Ukita, Riku Kanayama +21
Small Multi-Object Tracking (SMOT) is particularly challenging when targets occupy only a few dozen pixels, rendering detection and appearance-based association unreliable. Buildin…
GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers
Guang Liang, Xinyao Liu, Jianxin Wu
Vision Transformers (ViTs) are essential in computer vision but are computationally intensive, too. Model quantization, particularly to low bit-widths like 4-bit, aims to alleviate…